Wargames Powered by IBM
Watson: Multiplayer Real-Time
Strategy in 4D
An IBM® Redbooks® Point-of-View
publication
By Phaedra Boinodiris, IBM Global Leader Serious Games
and Gamification, Lisa Sokol, Ph.D, US Federal, IBM Office of
the CTO, Richard Behrens, IBM Watson Solution Architect,
and Hatte Blejer, Ph.D, Executive Architect, IBM Office of the
Public Sector CTO
Highlights
IBM Watson™ cognitive intelligence can
disrupt the way that you develop wargames
and train forces:
򐂰 Watson can be used to develop a
reusable gaming infrastructure
(city-state machine).
򐂰 Watson can be used to provide
guidance relative to doctrinal
compliance.
򐂰 4D gaming teaches users how to think
and act 10 moves ahead to develop fast
and resilient strategies.
򐂰 Time manipulation turns the game into a
contextual whiteboard, allowing the user
to see the consequences of their
strategy choices as the enemy adapts to
their tactics.
򐂰 Game lessons that are learned can
identify opportunities for doctrine and
strategy modification.
IBM Watson impacts serious games
Serious defense games have been around for decades. Many
defense implementations focus on skills training and first-person
shooter (FPS) gaming engines. The defense games have not
focused on games enabling Strategic Execution or Tactical
Operations. Strategic and tactical games require a complex
infrastructure that is based on the cascading rules that are
contained in doctrine. This type of game allows each mission
plan component to be vetted, stressed, and prioritized by the
entire decision and action chain.
Traditional game rule infrastructures are handcrafted by using
knowledge that is obtained from force doctrine, manuals, and
analytic models. City-state game machines use these rules to
control the play. The control portion of the machine is part data
and game infrastructure driven and part manually crafted. A
major impediment to the creation of a high-level strategy game
is the translation of force level doctrine into a form that the
city-state machine can use. The traditional approach to the
creation of a game's rule infrastructure does not scale to
high-level strategic games.
Imagine the creation of a Multiplayer Real-Time Strategy
(MRTS) game, which is played at the Commander-level and can
generate likely scenarios and cascading effects that are based
on rules that are generated automatically from doctrine.
Suppose that detailed adversary scenarios can be generated
automatically from information that is contained in books,
journals, and after-action reports. Data that is gathered from
stimulus-response exercises can help model how enemies
adapt to space and time conditions, current event data, and the
positioning of friendly troops and military assets.
Redbooks
© Copyright IBM Corp. 2014.
1
Figure 1 shows the envisioned gaming infrastructure
components.
Scenario Data
Game Values
Entities
Entities
Actions
Actions
Behaviors
Behaviors
Situations
Situations
Scenario
Player 1
P
Game
Engine
Player 2
P
Player 3
P
Watson
Hypothesis
Generation
Game Rule
Generation
Decomposed Doctrine
& Intelligence Database
Figure 1 Envisioned gaming infrastructure components
The generation of such an evolved game, as shown in
Figure 1, still requires the collection of a wide variety of
historical data, such as, geospatial data, weather, troop
activity, troop size, military asset types and counts,
geospatial grid, terrain, time of year, and battle
outcomes. Historical data-based models still can be
used to determine certain types of guidelines, for
example, potential adversary range of movement or
speed of movement.
Cognitive computing and
defense
A new computing approach is needed to process and
make sense of information and to enhance and extend
the expertise of humans. Effective navigation through
the current flood of unstructured information requires a
new era of computing, which is known as cognitive
systems. IBM® Watson™ is an example of a cognitive
system. Watson can use linguistic models to identify
inferences between text passages with human-like
accuracy and at speeds and scales that are far faster
and far bigger than any person can do on their own.
The Watson decomposed language components are
2
stored in a specialized database (shown in Figure 1)
form called triples. Different types of applications can
then use a combination of the data and higher-level
models to create specialized function, for example,
cancer diagnosis or to help automate call center
responses.
There are many different ways in which Watson can
contribute to serious games. The first way is to support
player strategy and doctrine questions. Watson based
systems use cognitive analytics and models to ingest
unstructured data and then save that information in a
structured form. Watson systems analyze a question
and then search potential responses in the database. It
then reexamines both the question and the answers in
hundreds of ways. Watson then uses the results to gain
a degree of confidence in its interpretation of the
question and potential answers. Watson responds to
the player with a set of potential answers, the likelihood
of the answer’s correctness, and the basis for that
answer. Watson manages a high level of accuracy
when it comes to understanding the correct answer to a
question. Properly trained, Watson answers a single
question and present rank-ordered evidence that drives
Watson hypotheses. The response, provided within a
matter of seconds, enables wargame players to
discover new evidence and identify new hypotheses
that were not considered previously, thus reducing
research time while improving analytic robustness and
completeness.
Both friendly and adversarial forces require separate
sets of doctrinal rules for control of the city-state game
machine. Watson technology can support the
automatic generation of doctrinal game rules that are
required by the city-state gaming infrastructure.
Watson can transform the information from relevant
unstructured data sources (for example, friendly and
adversary doctrine, manuals, after-action reports, and
manuals) into rules that can be used by the city-state
game machines to control the play. Watson then
discovers tactical and strategic rules relative to force
disposition, targets, threats, physical constraints
(including geography, weather, and physics), and
command and control networks. These automatically
generated rules are used to craft the basic
infrastructure of the game. Without Watson, the
creation of factors that drive detailed intelligence
assessments take months to produce.
Now, imagine a city simulation game where you play a
city manager trying to optimize city resources within the
confines of a stated budget. As part of gameplay, a
player determines how many fire stations to invest in
and where they are placed throughout the city to best
serve the city’s population.
Wargames Powered by IBM Watson: Multiplayer Real-Time Strategy in 4D
In a typical city simulation game, the game designer
determines (in the underlying mechanics of the game
or the city-state machine) the stated thresholds for
population density, how many fires will break out,
where the fires will break out, and which fires will be left
untreated given the current investment in fire
departments. Imagine this same game powered by
Watson cognitive intelligence, one that extracted basic
game design rules from, for example, planning
documents and lessons learned. The cognitively
generated infrastructure can provide rules to the
engine that details how likely fires are to break out and
where, given the current investments based on real
data.
Watson and 4D serious gaming
Watson can discover the infrastructure knowledge that
is required by Commander-level MRTS. It can discern
the rules that are embedded within complex doctrine
and force manuals. Watson can be used to discover
rules, cascading events, and related evidence. All of
this derived information can be transformed into a
city-state machine. The city-state machine is the
back-end infrastructure of a real-time strategy game.
The smart city-state machine can enable serious
gamers to explore tough strategy questions and
doctrine assessments.
Serious Games, when enabled by real data and real
processes, can be used for strategic execution and
tactical operations, boosting the value to organizations
through mission optimization (Figure 2).
Training
Exercises
Operations
Execution
Optimize
a process
With enhanced Serious Games, participants sort and
understand data, analyze issues, and test potential
solutions, applying variables that can be adjusted and
readjusted for different approaches. Game play
preserves doctrinally based engagement while
focusing players on important concerns and helping
transform their assumptions, skills, and behaviors.
4D Serious gaming: Time manipulation
and strategy exploration
Affording players the ability to manipulate time (the
fourth dimension (4D)) in multiplayer real-time strategy
games provides players the ability to optimize strategy
collectively in a way that maximizes resilience. Time
manipulation allows users to explore doctrine and its
implications within different gaming scenarios. 4D
game engines provide the ability for each player in a
multiplayer environment to affect change in different
positions on the timeline, which creates effects that
cascade to other players.
The ability for multiple players to collaboratively and
simultaneously edit a strategy across a timeline in real
time enables multiple subject matter experts (SMEs) to
work in concert collaboratively or adversarially. When
playing collaboratively, players can learn how their
strategies might conflict and where their strategies
might be complementary. When playing adversarially,
multiplayer time manipulation helps players explore the
strategy space of how their adversaries can thwart
plans, create distractions, and exploit weaknesses.
This approach fosters learning and allows players to
learn which offensive and defensive strategies are
more effective under what conditions. Players also
learn about the second- and third-order effects of
decisions.
Strategic
Tactical &
Optimizing
VBS2
Orchestration
Skill
Teach a process
Game play results help human strategists vet and
optimize strategy with the entire value chain based on
data sources from different domains. It is estimated
that gaming-enabled mission optimization will save
lives and might reduce cost and cycle time by as much
as 90% while improving result quality by more than
60%. Results also can include improvements in
margin, capacity, and capital reductions.
Figure 2 Teach a process
Games can teach players how to plan smarter, more
effective decisions within limited time frames. A
smarter serious game that is built on a Watson
enhanced city-state machine can enable the user to
view the game information and data in new ways,
allowing both experts and non-experts to understand
the doctrinally correct tactical and strategic choices.
Conclusion
Intelligence analysts seek to understand adversarial
intentions, doctrine, and capabilities that are
associated with mobile weapons platforms.
3
The adversary's actions depend heavily on force
disposition, targets, threats, physical constraints
(including geography, weather, and physics), and
command and control networks. These factors drive
detailed intelligence assessments containing analytical
judgments that take months to produce and are a static
representation of a dynamic battlespace with new (and
often obscure) intelligence constantly affecting the
outcomes.
Cognitive intelligence can provide a disruptive
approach to the generation of wargames that support
intelligence and defense wargame players. Watson can
support player strategy and doctrine questions. Watson
technology can support the automatic generation of
doctrinal game rules that are required by the city-state
gaming infrastructure. Watson can create a doctrinal
set of rules for each of the armed forces. Watson also
can create doctrinally correct rules for different
adversaries, using their own doctrinal handbooks and
authored memoirs. A Watson created infrastructure
can enable the vetting and optimization of strategy. The
use of a cognitive intelligence analytic to power a game
can revolutionize the way missions are planned,
organized, trained for, and vetted.
Temporal wargame manipulations can allow players to
evaluate and reevaluate the consequences of
decisions. It offers the ability to host a smarter
conversation about complex strategies by extrapolating
the complexity into a safe environment that can be
played through contextually. Warfighters can issue or
retract commands in the past, present, and future,
blurring the boundary between hypothetical and
committed decisions. In particular, the player can revisit
critical decision points, learn what decisions had the
most long-term impact, and use statistical information
on the timeline to make more informed decisions. 4D
support for multiple players to simultaneously change
history can further enhance training. Each player can
take advantage of an opponent's strategic weaknesses
in the past and each player can correct mistakes in
their own strategy and determine the best response to
their opponent. This approach helps players to
intuitively discover robust strategies.
help you design and implement your next generation
wargames.
IBM can help you craft a specialized version of a
Watson cognitive computing platform that can sift
through large quantities of unstructured data to
generate hypotheses and the supporting evidence. IBM
also can help the development of an infrastructure that
automatically can extract wargame rules, both friendly
and adversarial, from manuals, doctrine, textbooks,
and scholarly articles.
Resources for more information
For more information about the concepts that are
highlighted in this IBM Redbooks® Point-of-View
publication, see the following resources:
򐂰 IBM Watson:
http://www.ibm.com/smarterplanet/us/en/ibmwat
son/
򐂰 IBM Watson Explorer:
http://www.ibm.com/smarterplanet/us/en/ibmwat
son/explorer.html
򐂰 Implement Watson:
http://www.ibm.com/smarterplanet/us/en/ibmwat
son/implement-watson.html
򐂰 Smarter Serious Games:
http://www.ibm.com/smarterplanet/us/en/ibmwat
son/implement-watson.htm
򐂰 The Era of Cognitive Systems: An Inside Look at
IBM Watson and How it Works, REDP-4955
򐂰 Transforming the Way Organizations Think with
Cognitive Systems, REDP-4961
򐂰 Let's Play! Turning Serious Business Issues Into
Games, found at:
http://www.forbes.com/sites/ciocentral/2011/1
2/14/lets-play-turning-serious-business-issue
s-into-games/
򐂰 Serious solutions through serious games, found at:
http://vanguardcanada.uberflip.com/i/89342/27
What’s next: How IBM can help
IBM has an award-winning consulting practice that is
dedicated to both advanced serious games that can be
used to solve problems for organizations, and
gamification, using game design techniques as a
means to motivate user behavior. This consultancy can
4
򐂰 Boinodiris, et al., Serious Games for Business:
Using Gamification to Fully Engage Customers,
Employees and Partners, Meghan-Kiffer Press,
2014, ISBN 9780929652504
Wargames Powered by IBM Watson: Multiplayer Real-Time Strategy in 4D
Notices
This information was developed for products and services offered in the U.S.A.
IBM may not offer the products, services, or features discussed in this
document in other countries. Consult your local IBM representative for
information on the products and services currently available in your area. Any
reference to an IBM product, program, or service is not intended to state or
imply that only that IBM product, program, or service may be used. Any
functionally equivalent product, program, or service that does not infringe any
IBM intellectual property right may be used instead. However, it is the user's
responsibility to evaluate and verify the operation of any non-IBM product,
program, or service.
IBM may have patents or pending patent applications covering subject matter
described in this document. The furnishing of this document does not give you
any license to these patents. You can send license inquiries, in writing, to:
IBM Director of Licensing, IBM Corporation, North Castle Drive, Armonk, NY
10504-1785 U.S.A.
The following paragraph does not apply to the United Kingdom or any
other country where such provisions are inconsistent with local law:
INTERNATIONAL BUSINESS MACHINES CORPORATION PROVIDES THIS
PUBLICATION "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER
EXPRESS OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF NON-INFRINGEMENT, MERCHANTABILITY OR FITNESS
FOR A PARTICULAR PURPOSE. Some states do not allow disclaimer of
express or implied warranties in certain transactions, therefore, this statement
may not apply to you.
®
Trademarks
IBM, the IBM logo, and ibm.com are trademarks
or registered trademarks of International
®
Business Machines Corporation in the United
States, other countries, or both. These and
other IBM trademarked terms are marked on
their first occurrence in this information with the appropriate symbol (or),
indicating US registered or common law trademarks owned by IBM at the time
this information was published. Such trademarks may also be registered or
common law trademarks in other countries. A current list of IBM trademarks is
available on the Web at http://www.ibm.com/legal/copytrade.shtml
Redbooks
The following terms are trademarks of the International Business Machines
Corporation in the United States, other countries, or both:
IBM®
Redbooks®
Redbooks (logo)
Watson™
The following terms are trademarks of other companies:
Other company, product, or service names may be trademarks or service
marks of others.
This information could include technical inaccuracies or typographical errors.
Changes are periodically made to the information herein; these changes will be
incorporated in new editions of the publication. IBM may make improvements
and/or changes in the product(s) and/or the program(s) described in this
publication at any time without notice.
Any references in this information to non-IBM Web sites are provided for
convenience only and do not in any manner serve as an endorsement of those
Web sites. The materials at those Web sites are not part of the materials for
this IBM product and use of those Web sites is at your own risk.
IBM may use or distribute any of the information you supply in any way it
believes appropriate without incurring any obligation to you.
Information concerning non-IBM products was obtained from the suppliers of
those products, their published announcements or other publicly available
sources. IBM has not tested those products and cannot confirm the accuracy of
performance, compatibility or any other claims related to non-IBM products.
Questions on the capabilities of non-IBM products should be addressed to the
suppliers of those products.
This information contains examples of data and reports used in daily business
operations. To illustrate them as completely as possible, the examples include
the names of individuals, companies, brands, and products. All of these names
are fictitious and any similarity to the names and addresses used by an actual
business enterprise is entirely coincidental.
Any performance data contained herein was determined in a controlled
environment. Therefore, the results obtained in other operating environments
may vary significantly. Some measurements may have been made on
development-level systems and there is no guarantee that these
measurements will be the same on generally available systems. Furthermore,
some measurements may have been estimated through extrapolation. Actual
results may vary. Users of this document should verify the applicable data for
their specific environment.
COPYRIGHT LICENSE:
This information contains sample application programs in source language,
which illustrate programming techniques on various operating platforms. You
may copy, modify, and distribute these sample programs in any form without
payment to IBM, for the purposes of developing, using, marketing or
distributing application programs conforming to the application programming
interface for the operating platform for which the sample programs are written.
These examples have not been thoroughly tested under all conditions. IBM,
therefore, cannot guarantee or imply reliability, serviceability, or function of
these programs.
This document, REDP-5128-00, was created or updated on August 21, 2014.
© Copyright IBM Corp. 2014.
5